© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25721
    Prev
    Next
    INDEX
    Explanations

    for some reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fraser
    -0.14
    ardu
    -0.12
    --↵↵
    -0.11
    cken
    -0.11
    yr
    -0.11
    Č↵
    -0.10
    haar
    -0.10
    =~
    -0.10
     falsehood
    -0.10
     ultimately
    -0.10
    POSITIVE LOGITS
    ?
    0.08
    ane
    0.08
    sch
    0.08
     sheer
    0.07
     ID
    0.07
     raz
    0.07
    ANE
    0.07
     Hick
    0.07
    311
    0.07
     simultaneous
    0.06
    Activations Density 0.009%

    No Known Activations